About Xaira Therapeutics
Xaira is an innovative biotech startup focused on leveraging AI to transform drug discovery and development. The company is leading the development of generative AI models to design protein and antibody therapeutics, enabling the creation of medicines against historically hard-to-drug molecular targets. It is also developing foundation models for biology and disease to enable better target elucidation and patient stratification. Collectively, these technologies aim to continually enable the identification of novel therapies and to improve success in drug development. Xaira is headquartered in the San Francisco Bay Area, Seattle, and London.
AI in Residence
AI in Residence is a highly selective role at the intersection of frontier machine learning and drug discovery. Designed as an industry alternative to a traditional postdoctoral position, the program is for exceptional researchers and engineers who want to apply advanced AI to real biomedical problems end to end, from data to deployed systems. Residents join a small cohort working on high-impact AI efforts across Xaira. You'll collaborate closely with AI scientists, research engineers, and drug discovery teams to design, build, and ship machine learning capabilities that directly influence therapeutic programs. This is hands-on, system-level work with real scientific consequence. We're looking for candidates with technical depth, intellectual independence, strong research judgment, and evidence of delivering high-quality work—whether through publications, open-source, or production systems.
What You'll Do
- Develop and advance ML models for protein and antibody design using biophysical data, affinity data, library display data, protein structure datasets, and protein sequence datasets
- Design and implement scalable pipelines for data curation, training, evaluation, and inference integrated into discovery workflows
- Own projects end-to-end: problem framing → prototyping → validation → deployment
- Evaluate robustness and reliability (generalization, uncertainty, failure modes), plus interpretability where it supports scientific decision-making
- Contribute technical leadership by proposing new directions, shaping platform capabilities, and raising engineering/research standards through collaboration
You Might Work On
Examples include (not limited to):
- Foundation / representation models for protein/antibody structure, sequence and property modeling and prediction
- Methods for small, biased, noisy datasets; distribution shift; and uncertainty estimation.
- ML systems for experimental prioritization, assay interpretation, or translational signal discovery
- Evaluation frameworks and benchmarks tailored to discovery decision-making.
- Tooling that makes models usable by scientists (interfaces, automation, monitoring)
What Success Looks Like
- You ship one or more models or pipelines that are used in real discovery workflows.
- Your work improves decision quality (e.g., better prioritization, faster iteration, clearer uncertainty).
- You raise the bar on evaluation rigor and reproducibility (strong baselines, error analysis, reliable metrics)
- You leave behind maintainable systems (tests, documentation, monitoring) that others can build on
We Value
- Strong research judgment: choosing the right problems and knowing what "good evidence" looks like.
- Rigor: careful experimental design, ablations, error analysis, and honest reporting.
- Systems thinking: reliability, scalability, and maintainability—not just prototypes.
- Clear communication: writing, documentation, and sharing decisions/assumptions.
- Collaborative execution with scientific and engineering partners
Program Structure
Duration: 6–12 months
Start Dates: First hires beginning August 2026, with rolling applications and additional intakes in Fall 2026
Cohort Size: Small, highly selective cohort to enable meaningful ownership and close collaboration
Mentorship & Support
Dedicated technical mentor, plus structured feedback from senior AI, engineering, and scientific leadership
Publications & Presentations
We value scientific contribution and may support publications and conference presentations when appropriate. Publication scope and timing depend on project needs and are subject to internal review (e.g., IP and confidentiality). Authorship follows standard contribution-based guidelines.
Who Should Apply
We encourage applications from candidates who meet most of the following:
- Recent MS or PhD graduates (or equivalent research experience) in ML/AI, computational biology, biomedical engineering, or related fields
- Evidence of research excellence through high-quality publications or artifacts. Top venues (e.g., NeurIPS, ICML, ICLR, CVPR, ACL; Nature Methods, Cell Systems) are a plus, but strong preprints, open-source contributions, or shipped systems with demonstrated impact are equally compelling
- Demonstrated ability to lead substantial technical work with originality—new modeling ideas, rigorous experiments, or production-grade systems adopted by others
- Motivation to translate rigorous research into reliable, deployable AI systems that support therapeutic discovery
Please include a brief cover letter describing your interest in this role, why you're excited about this area, and what you hope to gain from the experience.
Compensation
The expected monthly compensation range is $10,000–$15,000, depending on experience and qualifications. We are open to higher compensation for candidates with exceptional experience or impact.